Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1378 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.2394. Min Range: -3.2394

Max Act: 3.1863. Min Act: -0.0002

Data Index: 1591930 (Python Code)

Max Activating Token Index: 896

Text #1

Max Range: 3.2394. Min Range: -3.2394

Max Act: 3.2394. Min Act: -0.0002

Data Index: 1428222 (Python Code)

Max Activating Token Index: 614

Text #2

Max Range: 3.2394. Min Range: -3.2394

Max Act: 1.8640. Min Act: -0.0002

Data Index: 1592119 (Python Code)

Max Activating Token Index: 645

Text #3

Max Range: 3.2394. Min Range: -3.2394

Max Act: 0.6995. Min Act: -0.0002

Data Index: 1568588 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 3.2394. Min Range: -3.2394

Max Act: 0.5263. Min Act: -0.0002

Data Index: 807900 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 3.2394. Min Range: -3.2394

Max Act: 0.4226. Min Act: -0.0002

Data Index: 607280 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 3.2394. Min Range: -3.2394

Max Act: 0.4563. Min Act: -0.0002

Data Index: 1413459 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 3.2394. Min Range: -3.2394

Max Act: 0.3704. Min Act: -0.0002

Data Index: 659080 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 3.2394. Min Range: -3.2394

Max Act: 0.2360. Min Act: -0.0002

Data Index: 1462563 (Python Code)

Max Activating Token Index: 851

Text #9

Max Range: 3.2394. Min Range: -3.2394

Max Act: 0.4331. Min Act: -0.0002

Data Index: 1529385 (Python Code)

Max Activating Token Index: 889

Text #10

Max Range: 3.2394. Min Range: -3.2394

Max Act: 0.2357. Min Act: -0.0002

Data Index: 1587485 (Python Code)

Max Activating Token Index: 588

Text #11

Max Range: 3.2394. Min Range: -3.2394

Max Act: 0.2838. Min Act: -0.0002

Data Index: 567372 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 3.2394. Min Range: -3.2394

Max Act: 0.2254. Min Act: -0.0002

Data Index: 14396 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 3.2394. Min Range: -3.2394

Max Act: 0.2070. Min Act: -0.0002

Data Index: 166492 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 3.2394. Min Range: -3.2394

Max Act: 0.1571. Min Act: -0.0002

Data Index: 635401 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 3.2394. Min Range: -3.2394

Max Act: 0.1610. Min Act: -0.0002

Data Index: 1597408 (Python Code)

Max Activating Token Index: 550

Text #16

Max Range: 3.2394. Min Range: -3.2394

Max Act: 0.1160. Min Act: -0.0002

Data Index: 950642 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 3.2394. Min Range: -3.2394

Max Act: 0.1248. Min Act: -0.0002

Data Index: 1608884 (Python Code)

Max Activating Token Index: 1023

Text #18

Max Range: 3.2394. Min Range: -3.2394

Max Act: 0.1158. Min Act: -0.0002

Data Index: 1560512 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 3.2394. Min Range: -3.2394

Max Act: 0.1082. Min Act: -0.0002

Data Index: 837129 (C4 (Web Text))

Max Activating Token Index: 1023